The textile industry is one of the most important industries in Sri Lanka.In most of the textile garment factories the defects of the fabrics are detected manually.The manual textile quality control usually depends on...The textile industry is one of the most important industries in Sri Lanka.In most of the textile garment factories the defects of the fabrics are detected manually.The manual textile quality control usually depends on eye inspection.Famously,human visual assessment is drawn-out,tiring,and an exhausting errand,including perception,consideration and experience to recognize the fault occurrence.The precision of human visual assessment declines with dull positions and vast schedules.Some of the time slow,costly,and sporadic review is the outcome.In this manner,the programmed automatic visual review safeguards both the fabric quality inspector and the quality.This examination has exhibited that Textile Defect Recognition System is fit for distinguishing fabrics’imperfections with endorsed exactness with viability.With some products 100%inspection is important to ensure the stipulated quality or standard.The classifications for the automated fabric inspection approaches are expanding as the work is vast and complex.According to the algorithm used,the texture analysis problem is classified into different approaches.They are Structural,spectral,model-based methods,Unfortunately,the optimal plan does not yet exist for these vast numbers of applied methods,as each of them has some advantages and disadvantages.展开更多
The inter-class face classification problem is more reasonable than the intra-class classification problem.To address this issue,we have carried out empirical research on classifying Indian people to their geographica...The inter-class face classification problem is more reasonable than the intra-class classification problem.To address this issue,we have carried out empirical research on classifying Indian people to their geographical regions.This work aimed to construct a computational classification model for classifying Indian regional face images acquired from south and east regions of India,referring to human vision.We have created an Automated Human Intelligence System(AHIS)to evaluate human visual capabilities.Analysis of AHIS response showed that face shape is a discriminative feature among the other facial features.We have developed a modified convolutional neural network to characterize the human vision response to improve face classification accuracy.The proposed model achieved mean F1 and Matthew Correlation Coefficient(MCC)of 0.92 and 0.84,respectively,on the validation set,outperforming the traditional Convolutional Neural Network(CNN).The CNN-Contoured Face(CNN-FC)model is developed to train contoured face images to investigate the influence of face shape.Finally,to cross-validate the accuracy of these models,the traditional CNN model is trained on the same dataset.With an accuracy of 92.98%,the Modified-CNN(M-CNN)model has demonstrated that the proposed method could facilitate the tangible impact in intra-classification problems.A novel Indian regional face dataset is created for supporting this supervised classification work,and it will be available to the research community.展开更多
With the development of wood industry, the processing of wood products becomemore significant. This paper discusses the developmen of machine vision system used to inspect andclassny the various types of defects of wo...With the development of wood industry, the processing of wood products becomemore significant. This paper discusses the developmen of machine vision system used to inspect andclassny the various types of defects of wood suxface. The surface defeds means the variations ofcolour and textUre. The machine vision system is to dated undesirable 'defecs' that can appear onthe surface of rough wood lwnber. A neural network was used within the Blackboard framework fora labeling verification step of the high-level recognition module of vision system. The system hasbere successfully tested on a number of boards from several different species.展开更多
In manufacture of precise optical products, it is important to inspect and classify the potential defects existing on the products’ surfaces after precise machining in order to obtain high quality in both functionali...In manufacture of precise optical products, it is important to inspect and classify the potential defects existing on the products’ surfaces after precise machining in order to obtain high quality in both functionality and aesthetics. The existing methods for detecting and classifying defects all are low accuracy or efficiency or high cost in inspection process. In this paper, a new inspection system based on machine vision has been introduced, which uses automatic focusing and image mosaic technologies to rapidly acquire distinct surface image, and employs Case-Based Reasoning(CBR)method in defects classification. A modificatory fuzzy similarity algorithm in CBR has been adopted for more quick and robust need of pattern recognition in practice inspection. Experiments show that the system can inspect surface diameter of 500mm in half an hour with resolving power of 0.8μm diameter according to digs or 0.5μm transverse width according to scratches. The proposed inspection principles and methods not only have meet manufacturing requirements of precise optical products, but also have great potential applications in other fields of precise surface inspection.展开更多
Coal is heterogeneous in nature,and thus the characterization of coal is essential before its use for a specific purpose.Thus,the current study aims to develop a machine vision system for automated coal characterizati...Coal is heterogeneous in nature,and thus the characterization of coal is essential before its use for a specific purpose.Thus,the current study aims to develop a machine vision system for automated coal characterizations.The model was calibrated using 80 image samples that are captured for different coal samples in different angles.All the images were captured in RGB color space and converted into five other color spaces(HSI,CMYK,Lab,xyz,Gray)for feature extraction.The intensity component image of HSI color space was further transformed into four frequency components(discrete cosine transform,discrete wavelet transform,discrete Fourier transform,and Gabor filter)for the texture features extraction.A total of 280 image features was extracted and optimized using a step-wise linear regression-based algorithm for model development.The datasets of the optimized features were used as an input for the model,and their respective coal characteristics(analyzed in the laboratory)were used as outputs of the model.The R-squared values were found to be 0.89,0.92,0.92,and 0.84,respectively,for fixed carbon,ash content,volatile matter,and moisture content.The performance of the proposed artificial neural network model was also compared with the performances of performances of Gaussian process regression,support vector regression,and radial basis neural network models.The study demonstrates the potential of the machine vision system in automated coal characterization.展开更多
Computer vision(CV)was developed for computers and other systems to act or make recommendations based on visual inputs,such as digital photos,movies,and other media.Deep learning(DL)methods are more successful than ot...Computer vision(CV)was developed for computers and other systems to act or make recommendations based on visual inputs,such as digital photos,movies,and other media.Deep learning(DL)methods are more successful than other traditional machine learning(ML)methods inCV.DL techniques can produce state-of-the-art results for difficult CV problems like picture categorization,object detection,and face recognition.In this review,a structured discussion on the history,methods,and applications of DL methods to CV problems is presented.The sector-wise presentation of applications in this papermay be particularly useful for researchers in niche fields who have limited or introductory knowledge of DL methods and CV.This review will provide readers with context and examples of how these techniques can be applied to specific areas.A curated list of popular datasets and a brief description of them are also included for the benefit of readers.展开更多
This paper proposes a machine-learning-based methodology to automatically classify different types of steel weld defects,including lack of the fusion,porosity,slag inclusion,and the qualified(no defects)cases.This met...This paper proposes a machine-learning-based methodology to automatically classify different types of steel weld defects,including lack of the fusion,porosity,slag inclusion,and the qualified(no defects)cases.This methodology solves the shortcomings of existing detection methods,such as expensive equipment,complicated operation and inability to detect internal defects.The study first collected percussed data from welded steel members with or without weld defects.Then,three methods,the Mel frequency cepstral coefficients,short-time Fourier transform(STFT),and continuous wavelet transform were implemented and compared to explore the most appropriate features for classification of weld statuses.Classic and convolutional neural network-enhanced algorithms were used to classify,the extracted features.Furthermore,experiments were designed and performed to validate the proposed method.Results showed that STFT achieved higher accuracies(up to 96.63%on average)in the weld status classification.The convolutional neural network-enhanced support vector machine(SVM)outperformed six other algorithms with an average accuracy of 95.8%.In addition,random forest and SVM were efficient approaches with a balanced trade-off between the accuracies and the computational efforts.展开更多
Purpose–This research aims to improve the performance of rail fastener defect inspection method for multi railways,to effectively ensure the safety of railway operation.Design/methodology/approach–Firstly,a fastener...Purpose–This research aims to improve the performance of rail fastener defect inspection method for multi railways,to effectively ensure the safety of railway operation.Design/methodology/approach–Firstly,a fastener region location method based on online learning strategy was proposed,which can locate fastener regions according to the prior knowledge of track image and template matching method.Online learning strategy is used to update the template library dynamically,so that the method not only can locate fastener regions in the track images of multi railways,but also can automatically collect and annotate fastener samples.Secondly,a fastener defect recognition method based on deep convolutional neural network was proposed.The structure of recognition network was designed according to the smaller size and the relatively single content of the fastener region.The data augmentation method based on the sample random sorting strategy is adopted to reduce the impact of the imbalance of sample size on recognition performance.Findings–Test verification of the proposed method is conducted based on the rail fastener datasets of multi railways.Specifically,fastener location module has achieved an average detection rate of 99.36%,and fastener defect recognition module has achieved an average precision of 96.82%.Originality/value–The proposed method can accurately locate fastener regions and identify fastener defect in the track images of different railways,which has high reliability and strong adaptability to multi railways.展开更多
When a customer uses the software, then it is possible to occur defects that can be removed in the updated versions of the software. Hence, in the present work, a robust examination of cross-project software defect pr...When a customer uses the software, then it is possible to occur defects that can be removed in the updated versions of the software. Hence, in the present work, a robust examination of cross-project software defect prediction is elaborated through an innovative hybrid machine learning framework. The proposed technique combines an advanced deep neural network architecture with ensemble models such as Support Vector Machine (SVM), Random Forest (RF), and XGBoost. The study evaluates the performance by considering multiple software projects like CM1, JM1, KC1, and PC1 using datasets from the PROMISE Software Engineering Repository. The three hybrid models that are compared are Hybrid Model-1 (SVM, RandomForest, XGBoost, Neural Network), Hybrid Model-2 (GradientBoosting, DecisionTree, LogisticRegression, Neural Network), and Hybrid Model-3 (KNeighbors, GaussianNB, Support Vector Classification (SVC), Neural Network), and the Hybrid Model 3 surpasses the others in terms of recall, F1-score, accuracy, ROC AUC, and precision. The presented work offers valuable insights into the effectiveness of hybrid techniques for cross-project defect prediction, providing a comparative perspective on early defect identification and mitigation strategies. .展开更多
In this paper, an automatic inspection system for weld surface appearance using machine vision has been developed to recognize weld surface defects such as porosities, cracks, etc. It can replace conventional manual v...In this paper, an automatic inspection system for weld surface appearance using machine vision has been developed to recognize weld surface defects such as porosities, cracks, etc. It can replace conventional manual visual inspection method, which is tedious, time-consuming, subjective, experience-depended, and sometimes biased. The system consists of a CCD camera, a self-designed annular light source, a sensor controller, a frame grabbing card, a computer and so on. After acquiring weld surface appearance images using CCD, the images are preprocessed using median filtering and a series of image enhancement algorithms. Then a dynamic threshold and morphology algorithms are applied to segment defect object. Finally, defect features information is obtained by eight neighborhoods boundary chain code algorithm. Experimental results show that the developed system is capable of inspecting most surface defects such as porosities, cracks with high reliability and accuracy.展开更多
This paper proposes an evolutionary optimized recurrent neural network for inspection of open/short defects on thin film transistor (TFT) lines of flat panel displays (FPD). The inspection is performed on digitized wa...This paper proposes an evolutionary optimized recurrent neural network for inspection of open/short defects on thin film transistor (TFT) lines of flat panel displays (FPD). The inspection is performed on digitized waveform data of voltage signals that are captured by a capacitor based non-contact sensor through scanning over TFT lines on the surface of mother glass of FPD. Irregular patterns on the waveform, sudden deep falls (open circuits) or sharp rises (short circuits), are classified and detected by employing the optimized recurrent neural network. The topology parameters of the recurrent neural network are optimized by a multiobjective evolutionary optimization process using a selected training data set. This method is an extension to our previous work, which utilized a feed-forward neural network, to address the drawbacks in it. Experimental results show that this method can detect defects on more realistic and noisy data than both of the previous method and the conventional threshold based method.展开更多
A robust system for backlit keyboard inspection is revealed. The backlit keyboard not only has changeable diverse colors but also has the laser marking keys. The keys on the keyboard can be divided into regions of fun...A robust system for backlit keyboard inspection is revealed. The backlit keyboard not only has changeable diverse colors but also has the laser marking keys. The keys on the keyboard can be divided into regions of function keys, normal keys, and number keys. However, there might have some types of defects: incorrect illuminating area, non-uniform illumination of specified inspection region(IR), and incorrect luminance and intensity of individual key. Since the illumination features of backlit keyboard are too complex to inspect for human inspector in the production line, an auto-mated inspection system for the backlit keyboard is proposed in this paper. The system was designed into the operation module and inspection module. A set of image processing methods were developed for these defects inspection. Some experimental results demonstrate the robustness and effectiveness of the proposed system.展开更多
This research aimed to improve selection of pepper seeds for separating high-quality seeds from low-quality seeds. Past research has shown that seed vigor is significantly related to the seed color and size, thus seve...This research aimed to improve selection of pepper seeds for separating high-quality seeds from low-quality seeds. Past research has shown that seed vigor is significantly related to the seed color and size, thus several physical features were identified as candidate predictors of high seed quality. Image recognition software was used to automate recognition of seed feature quality using 400 kernels of pepper cultivar 101. In addition, binary logistic regression and a neural network were applied to determine models with high predictive value of seed germination. Single-kernel germination tests were conducted to validate the predictive value of the identified features. The best predictors of seed vigor were determined by the highest correlation observed between the physical features and the subsequent fresh weight of seedlings that germinated from the 400 seeds. Correlation analysis showed that fresh weight was significantly positively correlated with eight physical features: three color features (R, a*, brightness), width, length, projected area, and single-kernel density, and weight. In contrast, fresh weight significantly negatively correlated with the feature of hue. In analyses of two of the highest correlating single features,' germination percentage increased from 59.3 to 71.8% when a*〉3, and selection rate peaked at 57.8%. Germination percentage increased from 59.3 to 79.4%, and the selection rate reached 76.8%, when single-kernel weight 〉0.0064 g. The most effective model was based on a multilayer perceptron (MLP) neural network, consisting of 15 physical traits as variables, and a stability calculated as 99.4%. Germination percentage in a calibration set of seeds was 79.1% and the selection rate was 90.0%. These results indicated that the model was effective in predicting seed germination based on physical features and could be used as a guide for quality control in seed selection. Automated systems based on machine vision and model classifiers can contribute to reducing the costs and labor required in the selection of pepper seeds.展开更多
Monitring pest populations in paddy fields is important to effectively implement integrated pest management.Light traps are widely used to monitor field pests all over the world.Most conventional light traps still inv...Monitring pest populations in paddy fields is important to effectively implement integrated pest management.Light traps are widely used to monitor field pests all over the world.Most conventional light traps still involve manual identification of target pests from lots of trapped insects,which is time-consuming,labor-intensive and error-prone,especially in pest peak periods.In this paper,we developed an automatic monitoring system for rice light-trap pests based on machine vision.This system is composed of an itelligent light trap,a computer or mobile phone client platform and a cloud server.The light trap firstly traps,kills and disperses insects,then collects images of trapped insects and sends each image to the cloud server.Five target pests in images are automatically identifed and counted by pest identification models loaded in the server.To avoid light-trap insects piling up,a vibration plate and a moving rotation conveyor belt are adopted to disperse these trapped insects.There was a close correlation(r=0.92)between our automatic and manual identification methods based on the daily pest number of one-year images from one light trap.Field experiments demonstrated the effectiveness and accuracy of our automatic light trap monitoring system.展开更多
In the proposed system for online inspection of steel balls, a diffuse illumination is developed to enhance defect appearances and produce high quality images. To fully view the entire sphere, a novel unfolding method...In the proposed system for online inspection of steel balls, a diffuse illumination is developed to enhance defect appearances and produce high quality images. To fully view the entire sphere, a novel unfolding method is put forward based on geometrical analysis, which only requires one-dimensional movement of the balls and a pair of cameras to capture images from different directions. Moreover, a realtime inspection algorithm is customized to improve both accuracy and efficiency. The precision and recall of the sample set were 87.7% and 98%, respectively. The average time cost on image processing and analysis for a steel ball was 47 ms, and the total time cost was less than 200 ms plus the cost of image acquisition and balls' movement. The system can sort 18 000 balls per hour with a spatial resolution higher than 0.01 mm.展开更多
A nonlinear visual mapping model is presented to replace the image Jacobian relation for uncalibrated hand/eye coordination. A new visual tracking controller based on artificial neural network is designed. Simulation ...A nonlinear visual mapping model is presented to replace the image Jacobian relation for uncalibrated hand/eye coordination. A new visual tracking controller based on artificial neural network is designed. Simulation results show that this method can drive the static tracking error to zero quickly and keep good robustness and adaptability at the same time. In addition, the algorithm is very easy to be implemented with low computational complexity.展开更多
A digital image analysis algorithm based color and morphological features was developed to identify the six varieties (ey7954, syz3, xs11, xy5968, xy9308, z903) rice seeds which are widely planted in Zhejiang Province...A digital image analysis algorithm based color and morphological features was developed to identify the six varieties (ey7954, syz3, xs11, xy5968, xy9308, z903) rice seeds which are widely planted in Zhejiang Province. Seven color and fourteen morphological features were used for discriminant analysis. Two hundred and forty kernels used as the training data set and sixty kernels as the test data set in the neural network used to identify rice seed varieties. When the model was tested on the test data set, the identification accuracies were 90.00%, 88.00%, 95.00%, 82.00%, 74.00%, 80.00% for ey7954, syz3, xs11, xy5968, xy9308, z903 respectively.展开更多
This paper introduces the identification of the defects on the fabric by using two-double neural network and wavelet analysis.The purpose is to fit for the automatic cloth inspection system and to avoid the disadvanta...This paper introduces the identification of the defects on the fabric by using two-double neural network and wavelet analysis.The purpose is to fit for the automatic cloth inspection system and to avoid the disadvantages of traditional human inspection.Firstly,training the normal fabric to acquire its characteristics and then using the BP neural network to tell the normal fabric apart from the one with defects.Secondly,doing the two-dimensional discrete wavelet transformation based on the image of the defects,then wiping off the proper characteristics of the fabric,and identifying the defects utilizing the trained BP neural network.It is proved that this method is of high speed and accuracy.It comes up to the requirement of automatic cloth inspection.展开更多
In this paper,an automated system and methodology for nondestructive sorting of apples are presented.Different from the traditional manual grading method,the automated,nondestructive sorting equipment can improve the ...In this paper,an automated system and methodology for nondestructive sorting of apples are presented.Different from the traditional manual grading method,the automated,nondestructive sorting equipment can improve the production efficiency and the grading speed and accuracy.Most popular apple quality detection and grading methods use two-dimensional(2D)machine vision detection based on a single charge-coupled device(CCD)camera detect the external quality.Our system integrates a 3D structured laser into an existing 2D sorting system,which provides the addition third dimension to detect the defects in apples by using the curvature of the structured light strips that are acquired from the optical system of the machine.The curvature of the structured light strip will show the defects in the apple surface.Other features such as color,texture,shape,size and 3D information all play key roles in determining the grade of an apple,which can be determined using a series of feature extraction methods.After feature extraction,a method based on principal component analysis(PCA)for data dimensionality reduction is applied to the system.Furthermore,a comprehensive classification method based on fuzzy neural network(FNN),which is a combination of knowledge-based and model-based method,is used in this paper as the classifier.Preliminary experiments are conducted to verity the feasibility and accuracy of the proposed sorting system.展开更多
文摘The textile industry is one of the most important industries in Sri Lanka.In most of the textile garment factories the defects of the fabrics are detected manually.The manual textile quality control usually depends on eye inspection.Famously,human visual assessment is drawn-out,tiring,and an exhausting errand,including perception,consideration and experience to recognize the fault occurrence.The precision of human visual assessment declines with dull positions and vast schedules.Some of the time slow,costly,and sporadic review is the outcome.In this manner,the programmed automatic visual review safeguards both the fabric quality inspector and the quality.This examination has exhibited that Textile Defect Recognition System is fit for distinguishing fabrics’imperfections with endorsed exactness with viability.With some products 100%inspection is important to ensure the stipulated quality or standard.The classifications for the automated fabric inspection approaches are expanding as the work is vast and complex.According to the algorithm used,the texture analysis problem is classified into different approaches.They are Structural,spectral,model-based methods,Unfortunately,the optimal plan does not yet exist for these vast numbers of applied methods,as each of them has some advantages and disadvantages.
文摘The inter-class face classification problem is more reasonable than the intra-class classification problem.To address this issue,we have carried out empirical research on classifying Indian people to their geographical regions.This work aimed to construct a computational classification model for classifying Indian regional face images acquired from south and east regions of India,referring to human vision.We have created an Automated Human Intelligence System(AHIS)to evaluate human visual capabilities.Analysis of AHIS response showed that face shape is a discriminative feature among the other facial features.We have developed a modified convolutional neural network to characterize the human vision response to improve face classification accuracy.The proposed model achieved mean F1 and Matthew Correlation Coefficient(MCC)of 0.92 and 0.84,respectively,on the validation set,outperforming the traditional Convolutional Neural Network(CNN).The CNN-Contoured Face(CNN-FC)model is developed to train contoured face images to investigate the influence of face shape.Finally,to cross-validate the accuracy of these models,the traditional CNN model is trained on the same dataset.With an accuracy of 92.98%,the Modified-CNN(M-CNN)model has demonstrated that the proposed method could facilitate the tangible impact in intra-classification problems.A novel Indian regional face dataset is created for supporting this supervised classification work,and it will be available to the research community.
文摘With the development of wood industry, the processing of wood products becomemore significant. This paper discusses the developmen of machine vision system used to inspect andclassny the various types of defects of wood suxface. The surface defeds means the variations ofcolour and textUre. The machine vision system is to dated undesirable 'defecs' that can appear onthe surface of rough wood lwnber. A neural network was used within the Blackboard framework fora labeling verification step of the high-level recognition module of vision system. The system hasbere successfully tested on a number of boards from several different species.
文摘In manufacture of precise optical products, it is important to inspect and classify the potential defects existing on the products’ surfaces after precise machining in order to obtain high quality in both functionality and aesthetics. The existing methods for detecting and classifying defects all are low accuracy or efficiency or high cost in inspection process. In this paper, a new inspection system based on machine vision has been introduced, which uses automatic focusing and image mosaic technologies to rapidly acquire distinct surface image, and employs Case-Based Reasoning(CBR)method in defects classification. A modificatory fuzzy similarity algorithm in CBR has been adopted for more quick and robust need of pattern recognition in practice inspection. Experiments show that the system can inspect surface diameter of 500mm in half an hour with resolving power of 0.8μm diameter according to digs or 0.5μm transverse width according to scratches. The proposed inspection principles and methods not only have meet manufacturing requirements of precise optical products, but also have great potential applications in other fields of precise surface inspection.
文摘Coal is heterogeneous in nature,and thus the characterization of coal is essential before its use for a specific purpose.Thus,the current study aims to develop a machine vision system for automated coal characterizations.The model was calibrated using 80 image samples that are captured for different coal samples in different angles.All the images were captured in RGB color space and converted into five other color spaces(HSI,CMYK,Lab,xyz,Gray)for feature extraction.The intensity component image of HSI color space was further transformed into four frequency components(discrete cosine transform,discrete wavelet transform,discrete Fourier transform,and Gabor filter)for the texture features extraction.A total of 280 image features was extracted and optimized using a step-wise linear regression-based algorithm for model development.The datasets of the optimized features were used as an input for the model,and their respective coal characteristics(analyzed in the laboratory)were used as outputs of the model.The R-squared values were found to be 0.89,0.92,0.92,and 0.84,respectively,for fixed carbon,ash content,volatile matter,and moisture content.The performance of the proposed artificial neural network model was also compared with the performances of performances of Gaussian process regression,support vector regression,and radial basis neural network models.The study demonstrates the potential of the machine vision system in automated coal characterization.
基金supported by the Project SP2023/074 Application of Machine and Process Control Advanced Methods supported by the Ministry of Education,Youth and Sports,Czech Republic.
文摘Computer vision(CV)was developed for computers and other systems to act or make recommendations based on visual inputs,such as digital photos,movies,and other media.Deep learning(DL)methods are more successful than other traditional machine learning(ML)methods inCV.DL techniques can produce state-of-the-art results for difficult CV problems like picture categorization,object detection,and face recognition.In this review,a structured discussion on the history,methods,and applications of DL methods to CV problems is presented.The sector-wise presentation of applications in this papermay be particularly useful for researchers in niche fields who have limited or introductory knowledge of DL methods and CV.This review will provide readers with context and examples of how these techniques can be applied to specific areas.A curated list of popular datasets and a brief description of them are also included for the benefit of readers.
基金support of Shanghai Pinlan Data Technology Co.,Ltd.,and Open Fund of Shanghai Key Laboratory of Engineering Structure Safety,SRIBS(No.2021-KF-06).
文摘This paper proposes a machine-learning-based methodology to automatically classify different types of steel weld defects,including lack of the fusion,porosity,slag inclusion,and the qualified(no defects)cases.This methodology solves the shortcomings of existing detection methods,such as expensive equipment,complicated operation and inability to detect internal defects.The study first collected percussed data from welded steel members with or without weld defects.Then,three methods,the Mel frequency cepstral coefficients,short-time Fourier transform(STFT),and continuous wavelet transform were implemented and compared to explore the most appropriate features for classification of weld statuses.Classic and convolutional neural network-enhanced algorithms were used to classify,the extracted features.Furthermore,experiments were designed and performed to validate the proposed method.Results showed that STFT achieved higher accuracies(up to 96.63%on average)in the weld status classification.The convolutional neural network-enhanced support vector machine(SVM)outperformed six other algorithms with an average accuracy of 95.8%.In addition,random forest and SVM were efficient approaches with a balanced trade-off between the accuracies and the computational efforts.
基金funded by the Key Research and Development Project of China Academy of Railway Sciences Corporation Limited(2021YJ310).
文摘Purpose–This research aims to improve the performance of rail fastener defect inspection method for multi railways,to effectively ensure the safety of railway operation.Design/methodology/approach–Firstly,a fastener region location method based on online learning strategy was proposed,which can locate fastener regions according to the prior knowledge of track image and template matching method.Online learning strategy is used to update the template library dynamically,so that the method not only can locate fastener regions in the track images of multi railways,but also can automatically collect and annotate fastener samples.Secondly,a fastener defect recognition method based on deep convolutional neural network was proposed.The structure of recognition network was designed according to the smaller size and the relatively single content of the fastener region.The data augmentation method based on the sample random sorting strategy is adopted to reduce the impact of the imbalance of sample size on recognition performance.Findings–Test verification of the proposed method is conducted based on the rail fastener datasets of multi railways.Specifically,fastener location module has achieved an average detection rate of 99.36%,and fastener defect recognition module has achieved an average precision of 96.82%.Originality/value–The proposed method can accurately locate fastener regions and identify fastener defect in the track images of different railways,which has high reliability and strong adaptability to multi railways.
基金Supported by the National Natural Science Foundation of China (No. 60872096) and the Fundamental Research Funds for the Central Universities (No. 2009B31914).
文摘When a customer uses the software, then it is possible to occur defects that can be removed in the updated versions of the software. Hence, in the present work, a robust examination of cross-project software defect prediction is elaborated through an innovative hybrid machine learning framework. The proposed technique combines an advanced deep neural network architecture with ensemble models such as Support Vector Machine (SVM), Random Forest (RF), and XGBoost. The study evaluates the performance by considering multiple software projects like CM1, JM1, KC1, and PC1 using datasets from the PROMISE Software Engineering Repository. The three hybrid models that are compared are Hybrid Model-1 (SVM, RandomForest, XGBoost, Neural Network), Hybrid Model-2 (GradientBoosting, DecisionTree, LogisticRegression, Neural Network), and Hybrid Model-3 (KNeighbors, GaussianNB, Support Vector Classification (SVC), Neural Network), and the Hybrid Model 3 surpasses the others in terms of recall, F1-score, accuracy, ROC AUC, and precision. The presented work offers valuable insights into the effectiveness of hybrid techniques for cross-project defect prediction, providing a comparative perspective on early defect identification and mitigation strategies. .
文摘In this paper, an automatic inspection system for weld surface appearance using machine vision has been developed to recognize weld surface defects such as porosities, cracks, etc. It can replace conventional manual visual inspection method, which is tedious, time-consuming, subjective, experience-depended, and sometimes biased. The system consists of a CCD camera, a self-designed annular light source, a sensor controller, a frame grabbing card, a computer and so on. After acquiring weld surface appearance images using CCD, the images are preprocessed using median filtering and a series of image enhancement algorithms. Then a dynamic threshold and morphology algorithms are applied to segment defect object. Finally, defect features information is obtained by eight neighborhoods boundary chain code algorithm. Experimental results show that the developed system is capable of inspecting most surface defects such as porosities, cracks with high reliability and accuracy.
文摘This paper proposes an evolutionary optimized recurrent neural network for inspection of open/short defects on thin film transistor (TFT) lines of flat panel displays (FPD). The inspection is performed on digitized waveform data of voltage signals that are captured by a capacitor based non-contact sensor through scanning over TFT lines on the surface of mother glass of FPD. Irregular patterns on the waveform, sudden deep falls (open circuits) or sharp rises (short circuits), are classified and detected by employing the optimized recurrent neural network. The topology parameters of the recurrent neural network are optimized by a multiobjective evolutionary optimization process using a selected training data set. This method is an extension to our previous work, which utilized a feed-forward neural network, to address the drawbacks in it. Experimental results show that this method can detect defects on more realistic and noisy data than both of the previous method and the conventional threshold based method.
文摘A robust system for backlit keyboard inspection is revealed. The backlit keyboard not only has changeable diverse colors but also has the laser marking keys. The keys on the keyboard can be divided into regions of function keys, normal keys, and number keys. However, there might have some types of defects: incorrect illuminating area, non-uniform illumination of specified inspection region(IR), and incorrect luminance and intensity of individual key. Since the illumination features of backlit keyboard are too complex to inspect for human inspector in the production line, an auto-mated inspection system for the backlit keyboard is proposed in this paper. The system was designed into the operation module and inspection module. A set of image processing methods were developed for these defects inspection. Some experimental results demonstrate the robustness and effectiveness of the proposed system.
基金supported by the Beijing Municipal Science and Technology Project,China (Z151100001015004)
文摘This research aimed to improve selection of pepper seeds for separating high-quality seeds from low-quality seeds. Past research has shown that seed vigor is significantly related to the seed color and size, thus several physical features were identified as candidate predictors of high seed quality. Image recognition software was used to automate recognition of seed feature quality using 400 kernels of pepper cultivar 101. In addition, binary logistic regression and a neural network were applied to determine models with high predictive value of seed germination. Single-kernel germination tests were conducted to validate the predictive value of the identified features. The best predictors of seed vigor were determined by the highest correlation observed between the physical features and the subsequent fresh weight of seedlings that germinated from the 400 seeds. Correlation analysis showed that fresh weight was significantly positively correlated with eight physical features: three color features (R, a*, brightness), width, length, projected area, and single-kernel density, and weight. In contrast, fresh weight significantly negatively correlated with the feature of hue. In analyses of two of the highest correlating single features,' germination percentage increased from 59.3 to 71.8% when a*〉3, and selection rate peaked at 57.8%. Germination percentage increased from 59.3 to 79.4%, and the selection rate reached 76.8%, when single-kernel weight 〉0.0064 g. The most effective model was based on a multilayer perceptron (MLP) neural network, consisting of 15 physical traits as variables, and a stability calculated as 99.4%. Germination percentage in a calibration set of seeds was 79.1% and the selection rate was 90.0%. These results indicated that the model was effective in predicting seed germination based on physical features and could be used as a guide for quality control in seed selection. Automated systems based on machine vision and model classifiers can contribute to reducing the costs and labor required in the selection of pepper seeds.
基金Supported by the Fundamental Public Welfare Research Program of Zhejiang Provincial Natural Science Foundation,China(LGN18C140007 and Y20C140024)the National High Technology Research and Development Program of China(863 Program,2013AA102402)the Agricultural Science and Technology Innovation Program of Chinese Academy of Agricultural Sciences.
文摘Monitring pest populations in paddy fields is important to effectively implement integrated pest management.Light traps are widely used to monitor field pests all over the world.Most conventional light traps still involve manual identification of target pests from lots of trapped insects,which is time-consuming,labor-intensive and error-prone,especially in pest peak periods.In this paper,we developed an automatic monitoring system for rice light-trap pests based on machine vision.This system is composed of an itelligent light trap,a computer or mobile phone client platform and a cloud server.The light trap firstly traps,kills and disperses insects,then collects images of trapped insects and sends each image to the cloud server.Five target pests in images are automatically identifed and counted by pest identification models loaded in the server.To avoid light-trap insects piling up,a vibration plate and a moving rotation conveyor belt are adopted to disperse these trapped insects.There was a close correlation(r=0.92)between our automatic and manual identification methods based on the daily pest number of one-year images from one light trap.Field experiments demonstrated the effectiveness and accuracy of our automatic light trap monitoring system.
文摘In the proposed system for online inspection of steel balls, a diffuse illumination is developed to enhance defect appearances and produce high quality images. To fully view the entire sphere, a novel unfolding method is put forward based on geometrical analysis, which only requires one-dimensional movement of the balls and a pair of cameras to capture images from different directions. Moreover, a realtime inspection algorithm is customized to improve both accuracy and efficiency. The precision and recall of the sample set were 87.7% and 98%, respectively. The average time cost on image processing and analysis for a steel ball was 47 ms, and the total time cost was less than 200 ms plus the cost of image acquisition and balls' movement. The system can sort 18 000 balls per hour with a spatial resolution higher than 0.01 mm.
基金This project was supported by the National Natural Science Foundation (No. 69875010).
文摘A nonlinear visual mapping model is presented to replace the image Jacobian relation for uncalibrated hand/eye coordination. A new visual tracking controller based on artificial neural network is designed. Simulation results show that this method can drive the static tracking error to zero quickly and keep good robustness and adaptability at the same time. In addition, the algorithm is very easy to be implemented with low computational complexity.
基金Project supported by the National Natural Science Foundation of China (No. 60008001) and the Natural Science Foundation ofZhejiang Province, China (No. 300297)
文摘A digital image analysis algorithm based color and morphological features was developed to identify the six varieties (ey7954, syz3, xs11, xy5968, xy9308, z903) rice seeds which are widely planted in Zhejiang Province. Seven color and fourteen morphological features were used for discriminant analysis. Two hundred and forty kernels used as the training data set and sixty kernels as the test data set in the neural network used to identify rice seed varieties. When the model was tested on the test data set, the identification accuracies were 90.00%, 88.00%, 95.00%, 82.00%, 74.00%, 80.00% for ey7954, syz3, xs11, xy5968, xy9308, z903 respectively.
文摘This paper introduces the identification of the defects on the fabric by using two-double neural network and wavelet analysis.The purpose is to fit for the automatic cloth inspection system and to avoid the disadvantages of traditional human inspection.Firstly,training the normal fabric to acquire its characteristics and then using the BP neural network to tell the normal fabric apart from the one with defects.Secondly,doing the two-dimensional discrete wavelet transformation based on the image of the defects,then wiping off the proper characteristics of the fabric,and identifying the defects utilizing the trained BP neural network.It is proved that this method is of high speed and accuracy.It comes up to the requirement of automatic cloth inspection.
文摘In this paper,an automated system and methodology for nondestructive sorting of apples are presented.Different from the traditional manual grading method,the automated,nondestructive sorting equipment can improve the production efficiency and the grading speed and accuracy.Most popular apple quality detection and grading methods use two-dimensional(2D)machine vision detection based on a single charge-coupled device(CCD)camera detect the external quality.Our system integrates a 3D structured laser into an existing 2D sorting system,which provides the addition third dimension to detect the defects in apples by using the curvature of the structured light strips that are acquired from the optical system of the machine.The curvature of the structured light strip will show the defects in the apple surface.Other features such as color,texture,shape,size and 3D information all play key roles in determining the grade of an apple,which can be determined using a series of feature extraction methods.After feature extraction,a method based on principal component analysis(PCA)for data dimensionality reduction is applied to the system.Furthermore,a comprehensive classification method based on fuzzy neural network(FNN),which is a combination of knowledge-based and model-based method,is used in this paper as the classifier.Preliminary experiments are conducted to verity the feasibility and accuracy of the proposed sorting system.